PaperMind - Multimodal Grounding: leaderboard
Metric: Judge score for writing the caption of a figure from a real paper given the paper's introduction, the original caption as reference; rated by a GPT-4o judge on a 5-point scale (1-5) against the reference, averaged over the seven scientific domains; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 2.39 |
| 2 | GPT-4o Mini | 2.18 |
| 3 | Claude 3.5 Sonnet | 2.14 |
| 4 | Qwen 3 VL 4B Instruct | 2.11 |
| 5 | Gemma 3 4B (IT) | 1.89 |
| 6 | Claude 3 Haiku | 1.87 |
Interactive version: theaggregate.ai/benchmark?slug=papermind-multimodal-grounding · How It Works · Data refreshed daily, snapshot 2026-10-07.